Загрузка видео...

Не удалось загрузить видео

На главную

Stock Analysis with AI Agents, using CrewAI 🚣 Using tools + LangSmith, running on Replit ⠕ A researcher, an analyst and an investment advisor Agents come together to built a recommendation on any stock out there ✨ lmk if you like and want more of this! 😉

128,742 просмотров • 2 лет назад •via X (Twitter)

Комментарии: 57

Фото профиля søren
søren2 лет назад

@LangChainAI @Replit awesome. stock analyzer bots were some of the first things i built + hosted on replit in 2020/2021. @notjustinshaw throwback to the days of scraping SPACs on and gpt-2 summarization.

Фото профиля Alger
Alger1 год назад

Looking to invest in the Enablers and Adopters of AI? Consider an actively managed fund investing in companies actively involved in developing and implementing AI technologies.

Фото профиля Mayo Oshin
Mayo Oshin2 лет назад

@LangChainAI @Replit Good job 👏 how can this approach be applied for general research on any topic?

Фото профиля João Moura
João Moura2 лет назад

@LangChainAI @Replit Pretty easy actually, just a matter of updating the agents and tasks, so it would be only updating prompts, maybe adding / removing agents depending on what you want. I’ll share another example this week of a trip planner crew as well with similar setup

Фото профиля Richard
Richard2 лет назад

@hwchase17 @LangChainAI @Replit Code?

Фото профиля João Moura
João Moura2 лет назад

@hwchase17 @LangChainAI @Replit dropping it next week, probably Tuesday together with a couple articles

Фото профиля Juancho
Juancho2 лет назад

@LangChainAI @Replit I did something similar to this but the analysis is still too basic in my opinion, specifically if you really want to do a serious investment. I was thinking to probably create 1K agents to bring this to the next level

Фото профиля João Moura
João Moura2 лет назад

@LangChainAI @Replit I think it’s maybe just a matter of having specific crews for what kind of analysis one would want, I tried to make this more generic, but if you want go deep and broad multiple crews are the way to go

Фото профиля PaulTheBully
PaulTheBully2 лет назад

@LangChainAI @Replit Is there a link to this tutorial?

Фото профиля João Moura
João Moura2 лет назад

@LangChainAI @Replit Not yet, I will be posting in the next couple days together with a couple articles

Фото профиля Pete Sena
Pete Sena2 лет назад

@LangChainAI @Replit Super cool use of AI agents

Фото профиля João Moura
João Moura2 лет назад

@LangChainAI @Replit right? Was pretty fun to build as well, but I have more cool examples to drop later this week 😎👉👉

Фото профиля Dave Hayes
Dave Hayes2 лет назад

@LangChainAI @Replit Certified dope.

Фото профиля João Moura
João Moura2 лет назад

@LangChainAI @Replit 🫡 I’ll keep it coming

Фото профиля Justin McCarty
Justin McCarty2 лет назад

@LangChainAI @Replit What is crew ai

Фото профиля João Moura
João Moura2 лет назад

@LangChainAI @Replit A thin framework to build groups of AI Agents ✨

Фото профиля João Moura
João Moura2 лет назад

idk if you saw this but another cool example similar to what we talked the other day

Фото профиля Evil Genius
Evil Genius2 лет назад

@LangChainAI @Replit Currently building something similar… Integrating into our platform…

Фото профиля Pablo Arango
Pablo Arango2 лет назад

@LangChainAI @Replit Hello, what is the software you use to record this kind of videos ?

Фото профиля João Moura
João Moura2 лет назад

@LangChainAI @Replit Screen Studio, pretty swett!

Фото профиля Jan
Jan2 лет назад

@LangChainAI @Replit Thanks for video. Really good explanation what's going on.

Фото профиля João Moura
João Moura2 лет назад

@LangChainAI @Replit Glad you linked Jan! So many great examples of things to build with AI Agents

Фото профиля Dog LLM
Dog LLM2 лет назад

@LangChainAI @Replit where’s source code

Фото профиля João Moura
João Moura2 лет назад

@LangChainAI @Replit Dropping in the few days together with a couple articles 🫡

Фото профиля João Moura
João Moura2 лет назад

check this one out, I think you might like it 😉

Фото профиля Troublemaker
Troublemaker2 лет назад

@LangChainAI @Replit Any code for this Stock Analysis AI Crew? Sounds like fun.

Фото профиля João Moura
João Moura2 лет назад

@LangChainAI @Replit will be sharing it later this week on the 21st together with a couple articles

Фото профиля Jason Ferrell
Jason Ferrell2 лет назад

@LangChainAI @Replit Cool, I built something similar using OpenAI’s assistant API. I found OpenAI to be rather slow, >1m per task run in GPT-4-turbo. Looks like you cut the demo for processing - how long do your agents take to complete their task runs?

Фото профиля João Moura
João Moura2 лет назад

@LangChainAI @Replit The whole thing takes around 5-10m, but that's doesn't bother me as much as I face it as basically time back for myself to do other things as it runs. That said smaller local models would be faster but lower quality. You can use them through @OLLAMA super good for simpelr tasks

Фото профиля Muratcan Koylan
Muratcan Koylan2 лет назад

@LangChainAI @Replit Great Job! Working on a similar project and CrewAI is really helpful 💫

Фото профиля João Moura
João Moura2 лет назад

@LangChainAI @Replit Thanks 🙏 I really appreciate hearing back from people using it ✨

Фото профиля Preet
Preet2 лет назад

@LangChainAI @Replit Good work brother.

Фото профиля João Moura
João Moura2 лет назад

@LangChainAI @Replit Thanks buddy! Was really fun to build!

Фото профиля Dr Shrivastava A(Generative AI Consultant)
Dr Shrivastava A(Generative AI Consultant)2 лет назад

@LangChainAI @Replit Super

Фото профиля Quang Dinh
Quang Dinh2 лет назад

@LangChainAI @Replit Great Job, I hope can try it.

Фото профиля João Moura
João Moura2 лет назад

@QuanginhNgc1 @LangChainAI @Replit Glad you liked it! CrewAI is opensource so feel free to give it a try, this example will be open sourced this week as well together with a couple articles I’ve been working on

Фото профиля Farid Safi
Farid Safi2 лет назад

@LangChainAI @Replit Good. Which software do you use for recording your camera ?

Фото профиля João Moura
João Moura2 лет назад

@LangChainAI @Replit Screen studio, pretty cool

Фото профиля Jeff Burke ⠕
Jeff Burke ⠕2 лет назад

@LangChainAI @Replit This is cool! Is the Repl public to fork?

Фото профиля João Moura
João Moura2 лет назад

@LangChainAI @Replit Will publish this week together with an article 😉

Фото профиля Daniel Kempe
Daniel Kempe2 лет назад

@LangChainAI @Replit 👍

Фото профиля Dariel Noel 🏆
Dariel Noel 🏆2 лет назад

@LangChainAI @Replit Wow😍 how do you ensure the accuracy and reliability of recommendations from these ai agents?

Фото профиля João Moura
João Moura2 лет назад

@LangChainAI @Replit Usually I'd measure this agains a testing set but a lot of this is built on live data, so I guess the best approach could be to have the report include all references for the data so you can double check if needed, if you include it in the prompt it should be able to do it

Фото профиля Fabian
Fabian2 лет назад

@LangChainAI @Replit this is awesome! great job with this chain.

Фото профиля The Content
The Content2 лет назад

@LangChainAI @Replit @memdotai mem it

Фото профиля 推文点赞|网站:mf8.xyz
推文点赞|网站:mf8.xyz2 лет назад

@LangChainAI @Replit 🔘🔳🔲,northerners are all cowards. one or two battles will end the

Фото профиля stagflacja
stagflacja2 лет назад

@LangChainAI @Replit Very cool. What takes the longest in this process - getting openai chat responses / generating embeddings / getting additional data from the internet? BTW is this app related to your framework, or just coincidence :)

Фото профиля João Moura
João Moura2 лет назад

@LangChainAI @Replit depends, because it's a non-linear process so sometimes it might do many embedding searches others not so much, but overall the OpenAI responses take the longest. Just a coincidence haha

Фото профиля hindu_interest
hindu_interest2 лет назад

@LangChainAI @Replit how to use this, website link please. Thank you

Фото профиля Danish Khan
Danish Khan2 лет назад

@LangChainAI @Replit What can be done to make the UI better?

Фото профиля Attila-IBS
Attila-IBS2 лет назад

@LangChainAI @Replit Has the stucked loop issue been fixed? I like this project, so I'd like to keep testing it, especially with Mixtral 8x7B

Фото профиля João Moura
João Moura2 лет назад

@LangChainAI @Replit It seems that stuck loop was me putting together a very bad readme example I didn't really tested 🙃 I updated the test but still didn't close the issue as I wanna add guardrails to prevent that. I'm super curious to try it with Mixtral as well! Thinking about fine tuning it

Фото профиля DongNan
DongNan2 лет назад

@LangChainAI @Replit .

Фото профиля ▓▒░cнroмυн░▒▓
▓▒░cнroмυн░▒▓2 лет назад

@LangChainAI @Replit How much did it cost for generating this?

Фото профиля João Moura
João Moura2 лет назад

@LangChainAI @Replit seems it was < $1 but I'll run more tests and report back

Фото профиля José
José2 лет назад

@LangChainAI @Replit @NotionAddon

Фото профиля Ryan Lisse
Ryan Lisse2 лет назад

@LangChainAI @Replit @memdotai mem it

Похожие видео

New Course: ACP: Agent Communication Protocol Learn to build agents that communicate and collaborate across different frameworks using ACP in this short course built with IBM Research's BeeAI, and taught by Sandi Besen, AI Research Engineer & Ecosystem Lead at IBM, and Nicholas Renotte, Head of AI Developer Advocacy at IBM. Building a multi-agent system with agents built or used by different teams and organizations can become challenging. You may need to write custom integrations each time a team updates their agent design or changes their choice of agentic orchestration framework. The Agent Communication Protocol (ACP) is an open protocol that addresses this challenge by standardizing how agents communicate, using a unified RESTful interface that works across frameworks. In this protocol, you host an agent inside an ACP server, which handles requests from an ACP client and passes them to the appropriate agent. Using a standardized client-server interface allows multiple teams to reuse agents across projects. It also makes it easier to switch between frameworks, replace an agent with a new version, or update a multi-agent system without refactoring the entire system. In this course, you’ll learn to connect agents through ACP. You’ll understand the lifecycle of an ACP Agent and how it compares to other protocols, such as MCP (Model Context Protocol) and A2A (Agent-to-Agent). You’ll build ACP-compliant agents and implement both sequential and hierarchical workflows of multiple agents collaborating using ACP. Through hands-on exercises, you’ll build: - A RAG agent with CrewAI and wrap it inside an ACP server. - An ACP Client to make calls to the ACP server you created. - A sequential workflow that chains an ACP server, created with Smolagents, to the RAG agent. - A hierarchical workflow using a router agent that transforms user queries into tasks, delegated to agents available through ACP servers. - An agent that uses MCP to access tools and ACP to communicate with other agents. You’ll finish up by importing your ACP agents into the BeeAI platform, an open-source registry for discovering and sharing agents. ACP enables collaboration between agents across teams and organizations. By the end of this course, you’ll be able to build ACP agents and workflows that communicate and collaborate regardless of framework. Please sign up here:

Andrew Ng

105,261 просмотров • 1 год назад